P$^2$-ViT: Power-of-Two Post-Training Quantization and Acceleration for Fully Quantized Vision Transformer

Documenti analoghi

• Trio-ViT: Post-Training Quantization and Acceleration for Softmax-Free Efficient Vision Transformer
  di: Shi, Huihong, et al.
  Pubblicazione: (2024)
• M$^2$-ViT: Accelerating Hybrid Vision Transformers with Two-Level Mixed Quantization
  di: Liang, Yanbiao, et al.
  Pubblicazione: (2024)
• CDM-QTA: Quantized Training Acceleration for Efficient LoRA Fine-Tuning of Diffusion Model
  di: Lu, Jinming, et al.
  Pubblicazione: (2025)
• IPTQ-ViT: Post-Training Quantization of Non-linear Functions for Integer-only Vision Transformers
  di: Kim, Gihwan, et al.
  Pubblicazione: (2025)
• An FPGA-Based Reconfigurable Accelerator for Convolution-Transformer Hybrid EfficientViT
  di: Shao, Haikuo, et al.
  Pubblicazione: (2024)